Autonomous Driving of Commercial Vehicles within

Cordoned Off Terminals

Nathalie Brenner

, Andreas Lauber

, Carsten Eckert

and Eric Sax

Karlsruhe Institute of Technology (KIT), Institute for Information Processing Technologies (ITIV),

76131 Karlsruhe, Germany

HPC Hamburg Port Consulting GmbH, 21129 Hamburg, Germany

Keywords:

Autonomous Vehicles, Commercial Vehicles, Terminal Infrastructure, Ports Trafﬁc Management.

Abstract:

In recent years, the development of autonomous trucks has progressed rapidly. It can be assumed that such

vehicles will be ready within the next decade. In order to make use of the advantages of automated driving

along the entire transport chain, it is necessary to use the autonomous vehicles on public roads as well as on

the terminal areas. The paper presents the extent to which it is possible to adopt autonomously driving trucks

to closed terminal areas. Further it discusses the technical, operational and legal requirements for vehicles,

transport service providers and terminals involved. Based on the requirements a concept for autonomous

driving of commercial vehicles in cordoned off areas is presented. Afterwards this concept is transformed

with the current processes on a fully automated container terminal into a concrete example. This example

shows how autonomous commercial vehicles can be integrated in the operational processes of an existing

terminal.

1 INTRODUCTION

In recent years, the development of Advanced Driver

Assistance Systems (ADAS) has progressed at a rapid

pace. Such vehicles are expected to offer cost savings,

better environmental performance, and higher safety

than conventional trucks. In view of increased compe-

tition and cost pressure in the transport sector, as well

as increased trafﬁc volumes and a simultaneous lack

of qualiﬁed drivers, it is important to exploit the op-

portunities arising from the use of autonomous trucks.

At the same time, Automated Guided Vehicles

(AGVs) for container transport within closed terminal

facilities already represent the state of the art and are

used successfully on a growing number of container

terminals worldwide. However, these vehicles are not

suitable for the use on public roads, since they depend

on the infrastructure, consisting of trafﬁc routes and

a guidance system. The autonomous vehicles have

to travel on public roads to a destination or terminal

and transport the goods to the corresponding destina-

tion within the depot. Therefore a clear distinction

between closed off terminals with AGVs and the pub-

lic road with trucks is made (see Figure 1). Therefore

the reaction on the environment is necessary.

Figure 1: Overview of the distinction of automated vehicles

within a port terminal.

In order to use autonomous driving along the en-

tire transport chain, autonomous commercial vehicles

have to be integrated into the operational processes on

a modern container terminal. The transfer of destina-

tion coordinates within the terminal and other infor-

mation requires communication between the vehicles,

infrastructure and transport service provider.

In this paper, Section 2 motivates the use of au-

tonomous commercial vehicles in cordoned-off areas.

Section 3 brieﬂy summarizes the state of the art for

automated vehicles in terminals and on public roads

and subsequently Section 4 presents a concept with

corresponding requirements for the operation of au-

tonomous vehicles in closed-off areas. This concept

will then be transferred in Section 5 to a fully au-

tomated container terminal. Finally, Section 6 con-

cludes with a summary and an outlook on future work.

Brenner, N., Lauber, A., Eckert, C. and Sax, E.

Autonomous Driving of Commercial Vehicles within Cordoned Off Terminals.

DOI: 10.5220/0007747905210527

In Proceedings of the 5th International Conference on Vehicle Technology and Intelligent Transport Systems (VEHITS 2019), pages 521-527

ISBN: 978-989-758-374-2

521

2 MOTIVATION FOR

AUTONOMOUS DRIVING

WITHIN TERMINALS

In the case of commercial vehicles in particular, it is to

be expected that new ADAS will offer the possibility

of increasing safety on public roads. It is foreseeable

that technological progress and the adaptation of the

legal framework conditions will make it possible for

autonomous vehicles to travel on public roads within

the next decades (Fagnant and Kockelman, 2015).

In addition, there is a signiﬁcant inﬂuence on

economic efﬁciency of commercial vehicles (Lauber

et al., 2016). On the one hand, personnel costs are a

big factor when considering total transportation costs,

on the other hand, autonomous vehicles can reduce

rest periods and therefore increase driving times. In

view of a lack of qualiﬁed candidates for the driver’s

job, there is almost no alternative but to expand the

sector of autonomous commercial vehicles in order to

guarantee the primary care through freight transport.

Although AGVs are already used in terminals,

they are not suitable for the use on public roads. This

is because of the strong dependence of AGVs on the

infrastructure. They usually have no sensors and act

according to the calculations of a central logic, as de-

scribed in Chapter 3.1. Due to the different condi-

tions on public roads and closed terminals the result-

ing technical and operational solutions are different

for AGVs and autonomous trucks. As the two solu-

tions are not compatible with each other they are spa-

tially separated (see Figure 2). For instance, on the

terminals the containers will be transported by AGVs

from the quay cranes to a container stack.

Within this area the containers are moved by auto-

mated stacking cranes.In order to enable the penetra-

tion of autonomous commercial vehicles the haulage

yards, service areas and terminals along the transport

chain must be prepared for the use of autonomous

vehicles. In addition, the requirements of the vehi-

cles must take into account the special conditions of

a container terminal, for instance the registration and

identiﬁcation at the entrance of a depot, compared to

public roads.

Therefore, this paper examines the use of au-

tonomously driving trucks on public roads and on cor-

doned off terminals. Further it will examine which

technical, operational, and legal requirements must be

met by the vehicles, the transport service providers,

and terminal infrastructure. The depots and port ter-

minals should be able to use autonomous trucks as

soon as industry is able to produce these. The result

of this study will be a road-map outlining the neces-

sary future development steps. This information can

Figure 2: Physical separation of the areas for manual and

autonomous vehicles and AGVs.

be taken into account in the development process. In

addition, closed-off areas offer the possibility of a test

ﬁeld, as they do not contradict the current legal situa-

tion.

3 STATE OF THE ART:

DRIVERLESS DRIVING

Autonomous vehicles are build for a movement on

public roads under various conditions. Therefore they

orientate themself within their environment through

built-in sensors. On the other hand, AGVs already

represent the current state of the art on terminals,

without self orientation and build-in sensors. In ad-

dition the current implementation of communication

systems is presented, because both concepts have a

need for a high data transfer rate.

3.1 Automated Guided Vehicles

Automatic vehicles for the transport of containers are

currently used in regular operating sequences at vari-

ous port terminals. For orientation and routing there

are no sensors on board of the AGVs or within the

infrastructure, but only a possibility for position de-

termination (e.g. via transponders or GNSS) and a

communication to a central logical unit (Evers and

Koppers, 1996). Due to the lack of on-board sensors

an obstacle avoidance is not possible with AGVs.

There are two concepts for the implementation of

those facilities. Either it is possible to realize the sys-

tems through central trafﬁc control (CT-control) or

through distributed trafﬁc control (DT-control). In

case of CT-control there is no information process-

ing, neither at the vehicle itself nor within the infras-

tructure (Evers and Koppers, 1996). The central log-

ical unit keeps track of the vehicle’s positions and

VEHITS 2019 - 5th International Conference on Vehicle Technology and Intelligent Transport Systems

522

Table 1: Comparision between Automated Guided Vehicles and Autonomous Vehicles.

Automated Guided Vehicle Autonomous Vehicles

CT DT

sensors none short range radar short range radar, long range

radar, optical sensors, lidar, etc

reaction to obstacles no obstacle detection

or reaction

obstacle detection obstacle detection and avoidance

logic centralized server centralized server and

on board

routing centralized server calculation on board

position communication via transmitter dGPS, etc.

communication required not required

movements at all times. The routes are calculated

completely by the control unit and communicated to

the AGVs. Due to the missing sensors on the vehi-

cle, an Automated Guided Vehicle (AGV) realized by

CT-control is not able to detect obstacles. Therefore

this procedure is not suitable for use on public roads.

It is only possible because the AGVs move within a

strictly monitored area without access of pedestrians

and other vehicles and therefore no incalculable ob-

stacles are present.

By using the concept of DT-control the communi-

cation with the AGV is reduced to a minimum. The

vehicles and parts of the infrastructure are equipped

with control units. The communication between the

central unit and the AGV is limited to a suggestion

of a route. The vehicle is equipped with short-range

radar sensors and has to react to its environment for it-

self. However, this reactivity consists of the detection

of objects and braking, but there is no possibility for

obstacle avoidance. After all this option is not suit-

able for use in areas with several automatic vehicles.

The mutual inﬂuence complicates the route calcula-

tion of the central unit. Therefore this variant also is

not suitable for simultaneous use on public roads.

All mentioned properties of both concepts,

CT-control and DT-control, are summarized in table 1

for a better overview.

3.2 Autonomous Vehicles

Autonomous vehicles are already being analyzed in

the last decades by many research projects and are

currently being evaluated by many manufacturers.

The feasibility has already been demonstrated in var-

ious demonstrations for individual trafﬁc situations.

For this purpose, the following should be particularly

noted ”Audi Piloted Driving” (Funke et al., 2012)

and ”Mercedes-Benz S500 Intelligent-Drive” (Ziegler

et al., 2014). Both have already demonstrated the

feasibility of autonomous driving using series com-

ponents in urban and rural areas years ago. But

also automotive suppliers like Bosch focusing on au-

tonomous driving within the last decades (Siegle

et al., 1992). In addition specialized companies (e. g.

Tesla (Tian et al., 2018), Waymo (Bresson et al.,

2017)) or data companies like Google (Brown, 2011)

started their work on autonomous driving. These ve-

hicles are based on standard technologies (camera, li-

dar, radar), as they are already used today in trucks

and cars. Processing this information by so-called

sensor fusion permits precise road holding and obsta-

cle avoidance. (Maurer et al., 2016)

Other institutions in particular the Research Cen-

ter for Computer Science focuses on the realiza-

tion and evaluation of novel ADAS. Due to the

development of the CoCar these systems and their

use can be tested under real environmental condi-

tions. (Forschungszentrum Informatik (FZI), 2019)

Table 1 summarizes the mentioned properties and

thus provides an overview of a direct comparison be-

tween AGVs and autonomous vehicles.

Although, at the beginning research has focused

primarily on autonomous passenger cars the advan-

tages of an autonomously driving truck are obvi-

ous. Next to more efﬁciency, higher safety and net-

working, and therefore a more sustainable transport

chain, economy, society and consumer will beneﬁt

equally (Wiesbaden, 2014). With regard to those

possibilities the ﬁeld of research of trucks has in-

creased. In 2014 Daimler was able to cover a longer

distance completely autonomously with the ”Future

Truck 2015” (Daimler AG, 2014). The basic idea was

the bundling and linking of all information and func-

tion of current and future assistance systems. Next to

the adaptive cruise control function, Stop-and-go and

Emergency brake systems, also lane keeping was in-

volved (Brockmann and Schlott, 2015). Furthermore

for efﬁcient driving a predictive gearshift program is

used. Predictive Powertrain Control provides infor-

mation about the upcoming road by combining the

navigation system and a three-dimensional map (Ter-

wen et al., 2004). Today the research ﬁeld of au-

Autonomous Driving of Commercial Vehicles within Cordoned Off Terminals

523

tonomous trucks are in no way inferior to passenger

cars. A further overview is given by additional lit-

erature (Kouchak and Gaffar, 2017). AGVs have

the goal to be guided in a cordoned of terminal and

autonomous trucks have the goal to drive on pub-

lic roads. Bringing both technologies together with-

out changing the speciﬁc behaviour of AGVs and the

trucks is focus of this study.

3.3 Communication Standards

In order to take advantage of autonomous vehicles,

trafﬁc telematics systems (Vehicle-to-X (V2X)) en-

able new assistance functions. Automated driving

functions are based on information of the vehicle’s

sensor systems (camera, radar, lidar, etc.). By con-

necting these systems, information between vehicles

can be exchanged. In order to realize a highly efﬁ-

cient data trafﬁc, the infrastructure e.g. trafﬁc lights,

trafﬁc signs and cameras on intersections are con-

nected to the systems as well. For V2X communi-

cation, the standards IEEE 802.11p and SAE J2735

have to be supported. However, V2X is not suitable

to transmit large amounts of data due to the low band-

width (DSRC (Dedicated Short Range Communica-

tion) Tech Cmte, 2016) and the limited range of 1 km.

Moreover, communication with vehicles is im-

portant for ﬂeet management of logistics operators.

Existing standards such as SAE J1939 and the ﬂeet

management system (FMS) are important factors.

This standardized interface enables the installation

of customer-speciﬁc systems into any vehicle. The

transmission of the data to the back-end server is

set up via the mobile network (GSM, UMTS, GPRS,

LTE, 5G) to connect vehicles at great distances.

4 CONCEPT FOR AUTONOMOUS

COMMERCIAL VEHICLES IN

RESTRICTED AREAS

As described in Section 3, various solutions have been

established for the applications public road and cor-

doned off terminals. Each adapted to the respective

requirements and boundary conditions, but are not

compatible with each other. For example, the termi-

nal’s IT system is presently not capable of integrating

autonomous vehicles as currently developed. More-

over AGVs are unable to drive on public roads.

In order to allow autonomous driving on roads and

terminals with the same vehicles, the approach of au-

tonomous vehicles appears to be more suitable. The

main reasons are safety, the structural complexity of

the infrastructure and the variety sensors installed in

autonomous road vehicles. Therefore, we focus our

work on the examination of how port terminals can be

prepared for the future use of autonomous trucks. In

addition to the boundary conditions, the legal aspects

have to be considered for setting the concept.

4.1 Technical Requirements

The basic technical realization of autonomous driv-

ing of cars and commercial vehicles has already been

proven as described in Section 3. Due to the different

challenges and boundaries the technical requirements

will be divided into three areas (vehicle, infrastructure

and communication).

4.1.1 Qualiﬁcation Proﬁle for Autonomous

Vehicles

Any external inﬂuences must be taken into account

in order to guarantee 24h/7 operation. Those inﬂu-

ence occur as weather conditions, differences in in-

cidence of light, but also as failure of system units

in the infrastructure. Therefore redundancies with re-

gard to the selection of sensors and passive fallback

levels are required for permanent operation. The ac-

quisition of environmental data has to take place with

radar sensors and cameras. In addition, trafﬁc signs

and changes in the environment must be taken into ac-

count. Therefore the longitudinal and lateral dynam-

ics have to be controlled by the autonomous vehicle.

Due to autonomous vehicles are already being ana-

lyzed by many manufactures, these requirements are

considered to be given along with all other assistance

systems.

In contrast to the previously mentioned claims,

there are requirements specially for the purpose of

driving on terminals with operational sequences. One

example is the vehicles availability to communicate

with the Terminal Operating System (TOS) in order

to report that the vehicle has reached a container han-

dover position and is waiting for the landing of the

container. Another one is the possibility to un- and

lock the ”twist locks” for securing the container on

the truck bed. Next to the vehicle, these requirements

are also valid to the infrastructure.

4.1.2 Infrastructural Requirements

Due to permission requirements to access the termi-

nal, the identiﬁcation of the truck is essential. This

can either be achieved by using cameras at the park-

ing spaces and at the terminal’s entry or via sending

and receiving an ID.

VEHITS 2019 - 5th International Conference on Vehicle Technology and Intelligent Transport Systems

524

This recognition is also crucial during loading and

unloading of the trucks. On the one hand the position

of the truck during the loading process has to be mon-

itored. On the other hand, it is necessary to check

whether the vehicle belongs together with the load

and the loads documents. With regard to the load-

ing process and its veriﬁcation, additional attention

should be paid to a high efﬁciency. The high through-

put and the crane position should be taken into ac-

count to reduce time losses caused by manoeuvring

the vehicles.

The position of the parking space has to be com-

municated in order to reach the assigned parking po-

sition by the truck. This could be achieved by trans-

mitting the GPS data or by route guidance through the

infrastructure. Since the truck is designed for driving

on public roads it is crucial that the infrastructure is

adapted to the road trafﬁc regulations. The given path

to the ﬁnal parking position may therefore be marked

only by light signals and trafﬁc signs. This saves fur-

ther demands on additional functions for routing in

the autonomous truck.

4.1.3 Communication Requirements

Communication takes place between all three parties,

truck, terminal and operator. The communication be-

tween truck and terminal is limited to slot planning

and parking position assignment. All further informa-

tion is communicated to the truck by its forwarding

company. The forwarding company communicated

with the terminal operator.

For exchanging of loading information from the

terminal to the forwarding company a high bandwidth

is required. Further the forwarding company have to

communicate with the autonomous vehicles, which

needs a long range communication. In order to in-

crease the range and bandwidth of the communica-

tion the mobile standards LTE and 5G should be sup-

ported.

4.2 Legal Aspects

In Europe, the Vienna Convention on Road Trafﬁc im-

poses a severe restriction on autonomous driving on

public roads. It states that a driver must be respon-

sible for the dynamic behavior of the vehicle at all

times. In contrast depots and port terminals are cor-

doned off areas are private property. Therefore, ﬁeld

tests for autonomous driving are moved to these areas.

The vehicles comply to general trafﬁc regulations in

public road transport, such as light and trafﬁc sights

or lane guidance. Furthermore no unforeseen situa-

tions, e.g. playing children or other pedestrians, are

expected. Thus, cordoned off areas offer the possi-

bility to investigate technical and operational require-

ments without having to deal with the current legal

obstacles.

Commercial vehicles have to ﬁnd their way inde-

pendently within port terminals. In addition to self-

driving, this also includes ﬁnding the allocated park-

ing space and ﬁnal parking action. This makes it suit-

able for testing mostly functions without violating the

legal framework.

5 EXAMPLE TERMINAL

The concept for the integration of autonomous com-

mercial vehicles has been presented. Within the scope

of the study, the project will be applied to a fully auto-

mated container terminal in Hamburg (Germany) for

the validation. This will be described in the following

section.

5.1 Current Operating Sequence

Today, a truck is steered through the terminal by a

driver which receives directions from the TOS. This

guides the truck through the terminal. Among other

information, they contain the control lanes, the trans-

fer position or the customs control zone.

Once the truck reached the assigned parking po-

sition at the container storage area the driver has to

prepare the trailer and ﬁnally report its readiness for

container handover. During the handover the drive

has to monitor the operation and instantly report any

irregularities to the crane operator. After the container

handover the driver has to prepare the truck for driv-

ing on public road. This includes setting of the twist

locks to secure the container on the trailer bed. Fig-

ure 3 shows exemplary the different locations on a

typical container terminal with a short description and

the tasks of the driver at those locations.

In case the container is not lifted from the trailer,

but the trailer remains at the terminal the driver has

to operate the trailer legs. Before leaving the terminal

with a new picked up trailer the driver has to perform

a quick check of the trailer’s road-worthiness.

Although in most modern container terminals

fright documents are already handled electronically,

sometimes the driver has to deliver and fetch certain

documents.

5.2 Planned Operating Sequence

Obviously, the operating sequence for an autonomous

truck differs from the current operation sequence.

Autonomous Driving of Commercial Vehicles within Cordoned Off Terminals

525

Figure 3: Locations on a container terminal a truck has to call at and the tasks the driver has to perform at those locations.

This is mainly due to the absence of the driver. As

a result, all communication with the truck (driving di-

rections, position reports, documents, etc.) has to be

done electronically. Since the trucks are build by dif-

ferent manufacturers and forwarding company vary

with their telematic system, an common interface sup-

porting all communication is not suitable. Therefore

only the forwarding company should communicate

with the truck (e. g. route of the truck) and infor-

mation should be send from the TOS company by a

deﬁned communication protocol.

As there is no communication between the truck

and the infrastructure, the infrastructure and the ter-

minal operator form a closed system. The au-

tonomous trucks receives the loading and route infor-

mation from the TOS via its forwarding company and

enters the terminal after successful identiﬁcation. The

intended parking position has to be communicated,

e.g. by GPS data. From now on the infrastructure

only guides the vehicles via public trafﬁc signs and

light signals. After reaching the parking position, the

crane operator has to be informed of the readiness for

loading, for example via the hazard warning light.

To reach the ﬁnal parking position the self-driving

of the truck is sufﬁcient, but in addition to the ac-

tual steering, currently the driver also performs fur-

ther manual tasks as described in Section 5.1. These

tasks must either be automated or performed by the

terminal personnel. In the ﬁrst case the automation of

supervision of container handover and securing twist

locks at the trailer can be done using sensors and

robotics. However, the economic and legal implica-

tions have to be analyzed in both cases. The driver

is currently responsible for securing the load on the

bed or opening the trailer for customs, which is then

transferred to the terminal operator (including liabil-

ity). After leaving the terminal the truck drives on

public road, as mentioned in the state of the art in Sec-

tion 3, to the customer depot or other terminals.

In order to guarantee a seamless transition from

manual operation to a fully automatic container termi-

nal, the study focuses a step-by-step approach of au-

tomation. Therefore all processes on the terminal has

to be prepared for an automatic operation, but also for

manual operation. This could be achieved by a spatial

separation of the handover positions for both kinds of

trucks.

6 CONCLUSION

In this paper, a motivation for the advancement of the

research for the combination of autonomous commer-

cial vehicles and automated terminals has taken place.

Therefore the state of the art in autonomous and auto-

matic vehicles was presented. Since AGVs will not be

able to move on public roads, the terminals will have

to be prepared for autonomous vehicles as they cur-

rently being researched by many manufacturers. For

realization, a concept was ﬁrst presented and subse-

quently the associated requirement were listed. In ad-

dition to the technical demands for the vehicle, the

infrastructure and the communication, the legal as-

pect was addressed too. Finally the concept was ap-

VEHITS 2019 - 5th International Conference on Vehicle Technology and Intelligent Transport Systems

526

plied to a fully automated container terminal for vali-

dation. For this reason the current operating sequence

was presented and extended to include the planned se-

quence.

Further steps within this study is a gap analy-

sis. The project investigates the extent to which it is

possible to use autonomously driving trucks on pub-

lic roads and simultaneously on closed terminal ar-

eas. Therefore the technical, operational and legal

requirements are examined. In addition to the pre-

sented demands for the vehicle, the requirements to

be met by the transport service providers and the ter-

minals are considered. In the further steps of the study

a detailed road map including requirements for au-

tonomous driving in terminals, the feasibility of the

concept and the saving potentials will be investigated.

ACKNOWLEDGEMENTS

This work has been funded by German Federal

Ministry of Transport and Digital Infrastructure

(BMVI) in the study INTERACt (funding number:

19H18005B)

REFERENCES

Bresson, G., Alsayed, Z., Yu, L., and Glaser, S. (2017). Si-

multaneous Localization and Mapping: A Survey of

Current Trends in Autonomous Driving. IEEE Trans-

actions on Intelligent Vehicles, 2(3):194–220.

Brockmann, S. and Schlott, S. (2015). Der weite weg zum

autonomen lkw-fahren. ATZ-Automobiltechnische

Zeitschrift, 117(1):8–13.

Brown, A. S. (2011). Hiding in Plain Sight: Google’s au-

tonomous car applies lessons learned from driverless

races. Mechanical Engineering, 133(02):31.

Daimler AG (2014). Future Truck 2025 - Weltpremiere f

den Transport der Zukunft.

DSRC (Dedicated Short Range Communication) Tech

Cmte (2016). Dedicated short range communications

(dsrc) message set dictionary

Evers, J. J. and Koppers, S. A. (1996). Automated

guided vehicle trafﬁc control at a container terminal.

Transportation Research Part A: Policy and Practice,

30(1):21 – 34.

Fagnant, D. J. and Kockelman, K. (2015). Preparing a

nation for autonomous vehicles: opportunities, barri-

ers and policy recommendations. Transportation Re-

search Part A: Policy and Practice, 77:167–181.

Forschungszentrum Informatik (FZI) (2019).

Cocar - the instrumented cognitive car.

http://www.fzi.de/project/cocar/.

Funke, J., Theodosis, P., Hindiyeh, R., Stanek, G., Kri-

tatakirana, K., Gerdes, C., Langer, D., Hernandez, M.,

Muller-Bessler, B., and Huhnke, B. (2012). Up to the

limits: Autonomous Audi TTS. In IEEE Intelligent

Vehicles Symposium (IV), 2012, pages 541–547, Pis-

cataway, NJ. IEEE.

Kouchak, S. M. and Gaffar, A. (2017). Determin-

ism in future cars: Why autonomous trucks are

easier to design. In 2017 IEEE SmartWorld,

Ubiquitous Intelligence Computing, Advanced

Trusted Computed, Scalable Computing Commu-

nications, Cloud Big Data Computing, Internet

of People and Smart City Innovation (Smart-

World/SCALCOM/UIC/ATC/CBDCom/IOP/SCI),

pages 1–6.

Lauber, A., Glock, T., Sax, E., and Wiedemann, M. (2016).

Analyzation and evaluation of vehicle and infrastruc-

ture for autonomous driving on public transportation

depots. In K. Berns, K. Dreßler, P. Fleischmann, R.

Ilsen, B. J

org, R. Kalmar, T. Nagel, C. Schindler, and

N. K. Stephan, editor, Commercial Vehicle Technol-

ogy, pages 3–12, Achen. Shaker Verlag.

Maurer, M., Gerdes, J. C., Lenz, B., and Winner, H. (2016).

Autonomous Driving: Technical, Legal and Social As-

pects. Springer Berlin Heidelberg, Berlin, Heidelberg.

Siegle, G., Geisler, J., Laubenstein, F., Nagel, H.-H., and

Struck, G. (1992). Autonomous driving on a road net-

work. In IEEE Intelligent Vehicles, 1992, pages 403–

408, Piscataway. IEEE.

Terwen, S., Back, M., and Krebs, V. (2004). Predictive pow-

ertrain control for heavy duty trucks. IFAC Proceed-

ings Volumes, 37(22):105–110.

Tian, Y., Pei, K., Jana, S., and Ray, B. (2018). DeepTest:

automated testing of deep-neural-network-driven au-

tonomous cars. In 2018 ACM/IEEE 40th International

Conference on Software Engineering, Piscataway, NJ.

IEEE.

Wiesbaden, S. F. (2014). Die zukunft hat bereits begonnen.

ATZ-Automobiltechnische Zeitschrift, 116(9):18–21.

Ziegler, J., Bender, P., Schreiber, M., Lategahn, H., Strauss,

T., Stiller, C., Dang, T., Franke, U., Appenrodt, N.,

Keller, C. G., Kaus, E., Herrtwich, R. G., Rabe, C.,

Pfeiffer, D., Lindner, F., Stein, F., Erbs, F., Enzweiler,

M., Knoppel, C., Hipp, J., Haueis, M., Trepte, M.,

Brenk, C., Tamke, A., Ghanaat, M., Braun, M., Joos,

A., Fritz, H., Mock, H., Hein, M., and Zeeb, E. (2014).

Making Bertha Drive—An Autonomous Journey on a

Historic Route. IEEE Intelligent Transportation Sys-

tems Magazine, 6(2):8–20.

Autonomous Driving of Commercial Vehicles within Cordoned Off Terminals

527